A Learnable Variational Model for Joint Multimodal MRI Reconstruction and Synthesis

被引:8
作者
Bian, Wanyu [1 ]
Zhang, Qingchao [1 ]
Ye, Xiaojing [2 ]
Chen, Yunmei [1 ]
机构
[1] Univ Florida, Gainesville, FL 32611 USA
[2] Georgia State Univ, Atlanta, GA 30302 USA
来源
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2022, PT VI | 2022年 / 13436卷
基金
美国国家科学基金会;
关键词
MRI reconstruction; Multimodal MRI synthesis; Deep neural network; Bilevel-optimization; IMAGE; ALGORITHM; ERROR;
D O I
10.1007/978-3-031-16446-0_34
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
Generating multi-contrasts/modal MRI of the same anatomy enriches diagnostic information but is limited in practice due to excessive data acquisition time. In this paper, we propose a novel deep-learning model for joint reconstruction and synthesis of multi-modal MRI using incomplete k-space data of several source modalities as inputs. The output of our model includes reconstructed images of the source modalities and high-quality image synthesized in the target modality. Our proposed model is formulated as a variational problem that leverages several learnable modality-specific feature extractors and a multimodal synthesis module. We propose a learnable optimization algorithm to solve this model, which induces a multi-phase network whose parameters can be trained using multi-modal MRI data. Moreover, a bilevel-optimization framework is employed for robust parameter training. We demonstrate the effectiveness of our approach using extensive numerical experiments.
引用
收藏
页码:354 / 364
页数:11
相关论文
共 26 条
[1]   An optimal control framework for joint-channel parallel MRI reconstruction without coil sensitivities [J].
Bian, Wanyu ;
Chen, Yunmei ;
Ye, Xiaojing .
MAGNETIC RESONANCE IMAGING, 2022, 89 :1-11
[2]   An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset [J].
Bian, Wanyu ;
Chen, Yunmei ;
Ye, Xiaojing ;
Zhang, Qingchao .
JOURNAL OF IMAGING, 2021, 7 (11)
[3]   Multimodal MR Synthesis via Modality-Invariant Latent Representation [J].
Chartsias, Agisilaos ;
Joyce, Thomas ;
Giuffrida, Mario Valerio ;
Tsaftaris, Sotirios A. .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2018, 37 (03) :803-814
[4]   Learnable Descent Algorithm for Nonsmooth Nonconvex Image Reconstruction [J].
Chen, Yunmei ;
Liu, Hongcheng ;
Ye, Xiaojing ;
Zhang, Qingchao .
SIAM JOURNAL ON IMAGING SCIENCES, 2021, 14 (04) :1532-1564
[5]   Model Learning: Primal Dual Networks for Fast MR Imaging [J].
Cheng, Jing ;
Wang, Haifeng ;
Ying, Leslie ;
Liang, Dong .
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT III, 2019, 11766 :21-29
[6]   Prior-Guided Image Reconstruction for Accelerated Multi-Contrast MRI via Generative Adversarial Networks [J].
Dar, Salman U. H. ;
Yurt, Mahmut ;
Shahdloo, Mohammad ;
Ildiz, Muhammed Emrullah ;
Tinaz, Berk ;
Cukur, Tolga .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2020, 14 (06) :1072-1087
[7]   Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks [J].
Dar, Salman U. H. ;
Yurt, Mahmut ;
Karacan, Levent ;
Erdem, Aykut ;
Erdem, Erkut ;
Cukur, Tolga .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2019, 38 (10) :2375-2388
[8]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[9]  
Hore Alain, 2010, Proceedings of the 2010 20th International Conference on Pattern Recognition (ICPR 2010), P2366, DOI 10.1109/ICPR.2010.579
[10]  
Iglesias JE, 2013, LECT NOTES COMPUT SC, V8149, P631, DOI 10.1007/978-3-642-40811-3_79